Skip to main content

A new mesh smoothing method based on a neural network

Abstract

As an elementary mesh quality improvement technique, smoothing has been widely used in finite element (FE) analysis. Heuristic smoothing methods and optimization-based smoothing methods are the two main smoothing types. The former is efficient. However, it operates heuristically and may create low-quality elements. In contrast, optimization-based smoothing is very effective at improving mesh quality. However, it suffers from high computational cost since it calculates the optimal position of a free node iteratively. In this paper, we present a new smoothing method. The proposed method imitates the optimization-based smoothing based on a neural network, but it calculates the optimal position of a free node straightforwardly. Hence, the proposed method is more efficient than these optimization-based smoothing methods while being comparable in terms of mesh quality. We present various testing results to illustrate the effectiveness of the proposed method.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20
Fig. 21
Fig. 22
Fig. 23

References

  1. 1.

    Kim J, Sastry SP, Shontz SM (2011) A numerical investigation on the interplay amongst geometry, meshes, and linear algebra in the finite element solution of elliptic PDEs. Eng Comput 28(4):431–450

    Article  Google Scholar 

  2. 2.

    G, Turk G (2001) Re-tiling polygonal surfaces. In: ACM SIGGRAPH computer graphics, vol 26, issue 2, 55–64

  3. 3.

    Liu J, Chen YQ, Sun SL (2009) Small polyhedron reconnection for mesh improvement and its implementation based on advancing front technique. Int J Numer Methods Eng 79(8):1004–1018

    MathSciNet  Article  Google Scholar 

  4. 4.

    Field DA (1988) Laplacian smoothing and Delaunay triangulations. Commun Appl Numer Methods 4(6):709–712

    Article  Google Scholar 

  5. 5.

    Lo SH (1985) A new mesh generation scheme for arbitrary planar domains. Int J Numer Methods Eng 21(8):1403–1426

    Article  Google Scholar 

  6. 6.

    Zhou T, Shimada K (2000) An angle-based approach to two-dimensional mesh smoothing. In: The 9th international meshing roundtable

  7. 7.

    Vartziotis D et al (2008) Mesh smoothing using the geometric element transformation method. Comput Methods Appl Mech Eng 197(45–48):3760–3767

    Article  Google Scholar 

  8. 8.

    Vartziotis D, Wipper J (2009) The geometric element transformation method for mixed mesh smoothing. Eng Comput 25(3):287–301

    Article  Google Scholar 

  9. 9.

    Vartziotis D, Wipper J (2012) Fast smoothing of mixed volume meshes based on the effective geometric element transformation method. Comput Methods Appl Mech Eng 201–204:65–81

    MathSciNet  Article  Google Scholar 

  10. 10.

    Leordeanu M, Hebert M (2008) Smoothing-based optimization. In: IEEE conference on computer vision & pattern recognition

  11. 11.

    Rabinovich M et al (2017) Scalable locally injective mappings. ACM Trans Graph 36(2):59–74

    Article  Google Scholar 

  12. 12.

    Shtengel A et al (2017) Geometric optimization via composite majorization. Acm Trans Graph 36(4):1–11

    Article  Google Scholar 

  13. 13.

    Feng JC, Chi KT (2014) Fundamentals of neural networks. Technometrics 37(4):1

    Google Scholar 

  14. 14.

    Jin L et al (2019) A survey on projection neural networks and their applications. Appl Soft Comput 76:533–544

    Article  Google Scholar 

  15. 15.

    Xu H, Newman TS (2006) An angle-based optimization approach for 2D finite element mesh smoothing. Finite Elem Anal Des 42(13):1150–1164

    MathSciNet  Article  Google Scholar 

  16. 16.

    Xu K, Gao X, Chen G (2018) Hexahedral mesh quality improvement via edge-angle optimization. Comput Graph 70:17–27

    Article  Google Scholar 

  17. 17.

    Kodiyalam PS (1991) A constrained optimization approach to finite element mesh smoothing. J Finite Elem Anal Des 9(4):309–320

    Article  Google Scholar 

  18. 18.

    Lo SH (1997) Optimization of tetrahedral meshes based on element shape measures. Comput Struct 63(5):951–961

    Article  Google Scholar 

  19. 19.

    Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2(5):359–366

    Article  Google Scholar 

  20. 20.

    Yue F, Chai T, Yue H (2010) Intelligent control using multiple models and neural networks. Int J Adapt Control Signal Process 22(5):495–509

    MathSciNet  MATH  Google Scholar 

  21. 21.

    Yin S, Yuschenko AS (2020) Object recognition of the robotic system with using a parallel convolutional neural network

  22. 22.

    Wysoski SG, Benuskova L, Kasabov N (2008) Adaptive spiking neural networks for audiovisual pattern recognition

  23. 23.

    Kobayashi H, Hara F (2019) The recognition of basic facial expressions by neural network. In: Proceedings 1991 IEEE international joint conference on neural networks

  24. 24.

    Goldberg Y (2016) A primer on neural network models for natural language processing. Comput Sci

  25. 25.

    Zamora-Martinez F, Castro-Bleda MJ (2018) Efficient embedded decoding of neural network language models in a machine translation system. Int J Neural Syst 1850007

  26. 26.

    Jung J, Yoon K, Lee PS (2020) Deep learned finite elements. Comput Methods Appl Mech Eng 372:113401

    MathSciNet  Article  Google Scholar 

  27. 27.

    Zhang L et al (2020) Hierarchical deep-learning neural networks: finite elements and beyond. Comput Mech 1–24

  28. 28.

    Saha S et al (2020) Hierarchical deep learning neural network (HiDeNN): an artificial intelligence (AI) framework for computational science and engineering. Comput Methods Appl Mech Eng 373:113452

    MathSciNet  Article  Google Scholar 

  29. 29.

    Jilani H, Bahreininejad A, Ahmadi MT (2009) Adaptive finite element mesh triangulation using self-organizing neural networks. Adv Eng Softw 40(11):1097–1103

    Article  Google Scholar 

  30. 30.

    Alfonzetti S, Dilettoso E, Salerno N (2008) An optimized generator of finite element meshes based on a neural network. IEEE Trans Magn 44(6):1278–1281

    Article  Google Scholar 

  31. 31.

    Álvarez R et al (2007) A mesh optimization algorithm based on neural networks. Inf Sci 177(23):5347–5364

    Article  Google Scholar 

  32. 32.

    Shewchuk JR (2002) What is a Good Linear Element? In: Interpolation conditioning & quality measures in proceedings of international meshing roundtable

  33. 33.

    Lee C, Lo S (1994) A new scheme for the generation of a graded quadrilateral mesh. Comput Struct 52(5):847–857

    Article  Google Scholar 

  34. 34.

    Maza S, Noel F, Leon JC (1999) Generation of quadrilateral meshes on free-form surfaces. Comput Struct 71(5):505–524

    MathSciNet  Article  Google Scholar 

  35. 35.

    Brewer ML et al (2003) The mesquite mesh quality improvement toolkit. In: Proceedings international meshing roundtable

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Yufei Guo.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Guo, Y., Wang, C., Ma, Z. et al. A new mesh smoothing method based on a neural network. Comput Mech (2021). https://doi.org/10.1007/s00466-021-02097-z

Download citation

Keywords

  • Mesh smoothing
  • Mesh
  • Neural network
  • Optimization-based smoothing